[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] [PATCH 5/6] x86/smp: Allocate pcpu stacks on their local numa node



On Tue, 2015-04-07 at 18:26 +0100, Andrew Cooper wrote:
> Previously, all pcpu stacks tended to be allocated on node 0.
> 
> Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
> CC: Keir Fraser <keir@xxxxxxx>
> CC: Jan Beulich <JBeulich@xxxxxxxx>
> 
Again, FWIW:

Reviewed-by: Dario Faggioli <dario.faggioli@xxxxxxxxxx>

Out of curiosity...

>  xen/arch/x86/smpboot.c |    2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c
> index a009e91..116c8f8 100644
> --- a/xen/arch/x86/smpboot.c
> +++ b/xen/arch/x86/smpboot.c
> @@ -642,7 +642,7 @@ static int cpu_smpboot_alloc(unsigned int cpu)
>      if ( node != NUMA_NO_NODE )
>          memflags = MEMF_node(node);
>  
> -    stack_base[cpu] = alloc_xenheap_pages(STACK_ORDER, 0);
> +    stack_base[cpu] = alloc_xenheap_pages(STACK_ORDER, memflags);
>
... I wonder how/why this was '0', while all the other were already
using MEMF_node(cpu_to_node)...

:-O

Regards,
Dario

Attachment: signature.asc
Description: This is a digitally signed message part

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel

 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.